The paper introduces ADFD‑Migrate, a method that extracts a latent declarative representation of code—an annotated data‑flow diagram (ADFD)—to aid large‑scale repository migration. By using an LLM to infer the source ADFD from repository context and guiding target‑language generation with dependency‑aware chunking, the approach improves porting soundness and completeness. Evaluated on 50 Fortran repositories, the system achieves high behavioral agreement and a superior migration outcome index compared to baseline translation methods.
arXiv:2610.09079v1 Announce Type: cross Abstract: Large language models equipped with development environments have moved code generation toward repository-scale construction, yet building complete r...
arXiv:2610.07832v1 Announce Type: cross Abstract: Large language models (LLMs) equipped with terminal access have demonstrated strong capabilities in automating software engineering tasks. However, e...
arXiv:2607. 08981v1 Announce Type: cross Abstract: LLM-generated code often compiles, passes tests, and appears correct, yet breaks once deployed.
The paper introduces Porting Benchmark, a curated dataset of 1,234 security patch backporting cases that span cross-version, cross-branch, and cross-repository scenarios, along with a common evaluation framework. Five tools—spanning program analysis, LLM prompting, and LLM agents—are evaluated under aligned settings, revealing that performance varies significantly across tools and that complex patches (Type-IV) see a sharp drop in success rate. The study identifies four root-cause categories for failures and demonstrates that reference-based benchmark scores may not fully capture real-world remediation, as executable validation uncovers additional integration issues.
SpecMine is a large-scale corpus that documents Spec-Driven Development (SDD) artifacts in public GitHub repositories. It includes a broad census of 470,795 spec files from 73,030 repositories linked to 17 tools, a focused census of 98,574 Kiro layout files from 12,910 repositories, and a sweep of 5,992 pull requests across 581 repositories that modify specs. The dataset provides enriched metadata, full commit histories, parsed document structures, and over 2.4 million typed references connecting specs to code, sibling documents, PRs, branches, and issues.
arXiv:2608. 09072v1 Announce Type: cross Abstract: Large language model-powered coding agents are increasingly used to modify existing code repositories, for example, by adding features or fixing bugs.
The paper introduces Porting Benchmark, a dataset of 1,234 security patch backporting cases covering cross-version, cross-branch, and cross-repository scenarios, along with a unified evaluation framework. Five tools—spanning program analysis, LLM prompting, and LLM agents—are evaluated under aligned settings, revealing that performance varies significantly across tools and patch complexity, with success rates dropping sharply for structurally complex patches. The study identifies four root-cause categories for failures and demonstrates that reference-based benchmark scores may not fully reflect real-world remediation, as executable validation uncovers additional integration issues.
arXiv:2511. 06090v3 Announce Type: replace-cross Abstract: Optimizing the performance of large-scale software repositories demands expertise in code reasoning and software engineering (SWE) to reduce runtime while preserving program correctness.
E2E-SWE is a benchmark that tests large language models’ ability to create complete, functional software repositories from scratch. It includes 186 tasks across 11 programming languages, each requiring an agent to build an installable project based solely on a natural‑language specification and an empty workspace, while passing a hidden test suite. The benchmark was crafted by software engineers and LLMs, then refined through iterative verification by autonomous agents to ensure clarity and solvability.
arXiv:2604. 07341v2 Announce Type: replace-cross Abstract: Most repository-level code translation and validation techniques have been evaluated on a single source-target programming language (PL) pair, owing to the complex engineering effort required to adapt new PL pairs.
The study examines whether the built‑in FAIL_TO_PASS (F2P) tests in repository‑level issue‑resolution benchmarks can be used to evaluate the runtime performance of patches that pass correctness tests. Using four advanced language models paired with SWE‑agent, the authors measured instruction counts and wall‑clock times for 262 cases and applied Welch ANOVA to detect performance differences. They found that many patches exhibit significant runtime disparities, that performance rankings often contradict issue‑resolution rates, and that some architectural regressions are revealed only through performance analysis.
arXiv:2607. 27146v1 Announce Type: cross Abstract: Coding agents have made substantial progress on software engineering tasks that modify existing codebases, including bug fixing and feature implementation.